The data set captures one week of Seattle Police Department ALPR activity obtained through public records requests.
Each time a license plate is detected by the ALPR device, the system records the date and time of the detection and the location of the license plate hit, including the exact longitude and latitude coordinates and the full address. This information revealed insight about the frequency and intensity of the surveillance program and the areas where it is used.
Our data set contains 93490 instances where license plates were detected by SPD’s surveillance system from 2021-10-01 00:02:08 to 2021-10-08 23:50:50. Of the license plates captured, 57237 reads, which accounts for 84% of the total reads, were only captured once. We also found that on average, each unique license plate was captured 1.37 times.
Figure 1 provides an overview of the geographic distribution of these reads. Nearly all of the non-Seattle reads are located along the journey to a prison north of Seattle. These reads were coded as “I-5”. We opted to remove these reads.
For a closer look, Figures 2, 3, and 4 depict zoomed-in maps that highlights areas with the highest concentration of ALPR reads through brighter colors. The most read-dense areas are located near SPD precincts. Notably, there are no reads in West Seattle and very few reads in East Capitol Hill and waterfront neighborhoods like Magnolia.
License plates are more likely to be captured on camera in the vicinity of SPD precincts.
While license plates all throughout downtown are likely to be captured by the ALPR system, we have observed that specific neighborhoods, such as East Capitol Hill, appear to go entirely unmonitored.
SPD’s North Precinct is located near the Northgate Transit Center, which suggests that the higher frequency of reads in this area may be due to patrol cars traveling to and from police headquarters.
The data set consists of 9 devices. Each device captured an average of 10388 license plates, with the most device capturing 21983 plates. Two devices were completely missing addresses, comprising 26% of all reads in the data. Another two devices were attached to parking enforcement officer vehicles (PEO). Reads from PEO devices account for 9% of reads in the data set.
The path of one active ALPR device is depicted below. The maps show where the device captured license plates on camera throughout the week
Contrary to our expectations, SPD devices were relatively inactive during the beginning of the work day. Figures 4 and 5 show that devices collected the most data in the middle of the work day, between 12:00 pm and 6:00 pm. On the busiest day in our data set, SPD cameras captured 22773 license plates. Up to 146 plates were captured in a single minute.
ALPR activity was busiest in the middle of the day.
ALPR activity was busiest on weekdays.